Kushner, S., Modi, V., Miolane, N.
Abstract
We leverage a family of Riemannian metrics to upsample low frame rate animations for creative design and compression applications in computer graphics. Our method interpolates animated characters’ bone orientations along various geodesics from a family of invariant Riemannian metrics on a product of SO(3) manifolds. For compression, an optimization step selects the best-fitting metric. We show that our approach outperforms existing techniques.
Citation
Kushner, S., Modi, V., Miolane, N. (2025) "Learning Riemannian Metrics for Interpolating Animations."
BibTeX
@article{kushner2025learning,
title = {Learning Riemannian Metrics for Interpolating Animations},
author = {Sarah Kushner and Vismay Modi and Nina Miolane},
year = {2025},
conference = {Geometric Science of Information}
}
